Energy storage sizing in plug-in Electric Vehicles: Driving cycle uncertainty effect analysis and machine learning based sizing framework

Bansal, Sakshi; Dey, Satadru; Khanra, Munmun

doi:10.1016/j.est.2021.102864

Cited by 17 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concerning the validation methods, 25 of the selected studies use them to assess the prediction accuracy of ECEV models. As can be seen in Figure 10, the cross-validation method is the most frequently used in 15 studies [36,[47][48][49]64,71,102,106,109,111,115,120,121,160,164], followed by 10-fold cross-validation in 10 studies [41,43,51,52,83,103,141,147,165,170], 5-fold cross-validation in 6 studies [91,94,108,152,158,167], then 3-fold cross-validation in 3 studies [92,93,152]. Less studied cross-validations methods are not shown in Figure 10, such as 1-2-4-fold cross validation [152], 6-fold cross validation [137], 8-fold cross validation [146], 9-fold cross-validation [122], and leave-one-out cross-validation [83] which are in only 1 study each.…”

Section: Evaluation Measures and Validation Methodsmentioning

confidence: 99%

“…References N • of Studies ML-based EMS [23][24][25]27,[29][30][31]33,[35][36][37]39,40,42,45,49,53,55,58,60,61,[65][66][67]69,70,73,74,77,88,90,91,98,100,104,105,113,126,129,132,133,135,136,139,141,146,149,156,166,174] 50 ML-based speed profile prediction [19]…”

Section: Resolution Approachesmentioning

confidence: 99%

“…Thus, optimizing them is required. Of the selected studies, only 22 studies use optimization methods, 10 studies use Grid search (GS) [43,51,52,71,83,106,141,158,164,165], 5 studies the use genetic algorithm [96,100,115,140,169], 4 studies [36,160,165,173] use particle swarm optimization (PSO), and 2 studies use random search [132,146]. Other optimization methods are less used such as Bayesian optimization [132], Fine-tuning [138], least mean squared (LMS) optimization [162], lightning search algorithm, backtracking search optimization, and gravitational search algorithm [160], each one being used in only one study.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Efficient Management of Energy Consumption of Electric Vehicles Using Machine Learning—A Systematic and Comprehensive Survey

2023

View full text Add to dashboard Cite

Electric vehicles are growing in popularity as a form of transportation, but are still underused for several reasons, such as their relatively low range and the high costs associated with manufacturing and maintaining batteries. Many studies using several approaches have been conducted on electric vehicles. Among all studied subjects, here we are interested in the use of machine learning to efficiently manage the energy consumption of electric vehicles, in order to develop intelligent electric vehicles that make quick unprogrammed decisions based on observed data allowing minimal electricity consumption. Our interest is motivated by the adequate results obtained using machine learning in many fields and the increasing but still insufficient use of machine learning to efficiently manage the energy consumption of electric vehicles. From this standpoint, we have built this comprehensive survey covering a broad variety of scientific papers in the field published over the last few years. According to the findings, we identified the current trend and revealed future perspectives.

show abstract

Section: Evaluation Measures and Validation Methodsmentioning

confidence: 99%

Section: Resolution Approachesmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Efficient Management of Energy Consumption of Electric Vehicles Using Machine Learning—A Systematic and Comprehensive Survey

2023

View full text Add to dashboard Cite

show abstract

“…In the context of electric vehicles, driving cycles play a fundamental role in determining energy consumption and, ultimately, vehicle autonomy. In this particular research, we used three common cycles to explore energy consumption: the new European driving cycle (NEDC), worldwide harmonized light vehicle test cycle type 2 (WLTC-2), and type 3 (WLTC-3) [27][28][29].…”

Section: Driving Cyclesmentioning

confidence: 99%

Influence of the Final Ratio on the Consumption of an Electric Vehicle under Conditions of Standardized Driving Cycles

et al. 2021

View full text Add to dashboard Cite

Electric vehicles must improve their electric drive system efficiency and effectively use their limited energy to become a viable means of transportation. As such, these technologies have undergone substantial improvements from their initial conception. More efficient powertrains, together with improved storage technologies, have enabled more extended autonomy. However, from an engineering perspective, these systems are still a key area of research and optimization. This work presents a powertrain optimization methodology, developing energy savings and improving the performance of the electric vehicle by focusing on the differential. The proposed methodology includes a study of the dynamics of the electric vehicle and the generation of a mathematical model that represents it. By simulating the vehicle and varying the final ratio of the differential, a significant optimization for energy savings is obtained by developing a standardized driving cycle. In this case, NEDC, WLTC-2, and WLTC-3 test cycles are used. The results show that a short ratio improves performance, even if this implies a larger torque from the prime mover. Depending on the operating cycle used, an energy-saving between 3% and 8% was registered. An extended energy autonomy and an increment in the life-cycle of the batteries are expected in real driving scenarios.

show abstract

“…The objective was to gather a diverse range of information from these papers, encompassing 9 distinct features. By incorporating these features, our aim was to develop ML models capable of predicting SC behavior across a broad spectrum of conditions [31,32]. The inclusion of all relevant input characteristics is a pivotal phase in the construction of ML models, enabling the models to capture the essential aspects of the experimental research while accounting for the significant factors impacting SC performance.…”

Section: Introductionmentioning

confidence: 99%

Modeling specific capacitance of carbon nanotube-based supercapacitor electrodes by machine learning algorithms

Tawfik,

Abdel-Wahab,

Lee

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

Carbon nanotubes (CNTs) have emerged as promising materials for supercapacitors (SCs) due to their unique properties and exceptional electrical conductivity. These cylindrical structures composed of carbon atoms offer several advantages for SC electrode applications. The electrochemical performance of CNT-based electrodes is strongly influenced by factors such as surface area, pore structure, and ID/IG ratio. However, the lack of a credible physical model capable of accurately predicting the performance of SCs based on these physicochemical properties of CNTs poses a challenge. In this study, we propose the utilization of a data-driven approach employing various models including a gradient boosting regression (GBR), Bayesian regression (BR), ridge regression (RR), and stochastic gradient descent (SGD) model to predict the performance of SCs with CNT electrodes based on the microstructural properties of the electrode material and electrochemical operational parameters. The developed GBR model demonstrates its feasibility by achieving a low root mean square error (RMSE) value of approximately 36.31 for the prediction of specific capacitance for test split. Additionally, a sensitivity analysis was conducted to investigate the influence of independent input parameters on a single output parameter, specifically the specific capacitance. This analysis provides insights into the relative importance and impact of various input parameters on the specific capacitance of CNT-based SCs.

show abstract

Energy storage sizing in plug-in Electric Vehicles: Driving cycle uncertainty effect analysis and machine learning based sizing framework

Cited by 17 publications

References 25 publications

Efficient Management of Energy Consumption of Electric Vehicles Using Machine Learning—A Systematic and Comprehensive Survey

Efficient Management of Energy Consumption of Electric Vehicles Using Machine Learning—A Systematic and Comprehensive Survey

Influence of the Final Ratio on the Consumption of an Electric Vehicle under Conditions of Standardized Driving Cycles

Modeling specific capacitance of carbon nanotube-based supercapacitor electrodes by machine learning algorithms

Contact Info

Product

Resources

About